1.College of Mechanical and Vehicle Engineering,Hunan University,Changsha 410082,China
2.Wuxi Intelligent Control Research Institute of Hunan University,Wuxi 214115,China
Show less
文章历史+
Received
Published
2024-03-12
2025-08-25
Issue Date
2026-02-12
PDF (2534K)
摘要
同时定位与建图(simultaneous localization and mapping, SLAM)技术在自动驾驶领域有着广泛的应用,其中精度和计算效率是SLAM最重要的两个指标.然而,传统的激光雷达里程计难以准确高效地提取关键帧,导致构建地图时包含了过多的冗余帧.此外,大多数激光里程计需要对每一帧执行帧到地图的对齐,这带来了高额的计算负担.本文提出了一种基于关键帧的双模式激光里程计与建图方法,通过计算两帧点云之间的特征相似度并将其与运动自适应阈值进行比较,提取关键帧.随后,对关键帧和非关键帧执行不同的配准算法,旨在最小化计算资源的消耗.此外,利用点的水平距离信息计算权重函数,并将其整合到加权位姿约束中.本文提出的SLAM系统在KITTI数据集和实车上进行了大量试验,KITTI序列00-10的结果显示,平移误差仅有0.56%,在旋转上的误差为0.002 1(°)/m.实时性方面,与F-LOAM相比,本文算法将平均速度提高了26.5%,比轻量级系统LeGO-LOAM更快.
Abstract
Simultaneous localization and mapping (SLAM) technology is widely used in the field of autonomous driving, where accuracy and computational efficiency are the two most important indicators. However, traditional LiDAR odometry faces challenges in accurately and efficiently extracting keyframes, resulting in an excess of redundant frames during map construction. Additionally, the majority of LiDAR odometry systems require aligning each frame to the map, which imposes a substantial computational burden. This paper proposes a dual-mode LiDAR odometry and mapping method based on keyframes. By computing the feature similarity between two point clouds and comparing it with a motion-adaptive threshold, keyframes are extracted. Subsequently, different registration algorithms are applied to keyframes and non-keyframes to minimize computational resource consumption. Furthermore, a weight function is calculated using point horizontal distance information and integrated into the weighted pose constraints. The SLAM system proposed undergoes extensive testing on the KITTI dataset and real vehicles. The results from KITTI sequences 00-10 demonstrate a translational error of only 0.56% and a rotational error of 0.002 1 degree/m. In terms of real-time performance, compared with F-LOAM, our algorithm improves average speed by 26.5%, and even outperforms lightweight system LeGO-LOAM.
为了评估本文提出的关键帧检测方法与传统方法之间的优劣,我们引入了一组消融试验,标记为nk.在这组试验中,关键帧检测方法被替换为LIO-SAM所采用的传统方法,该方法基于空间距离和角度变化过滤关键帧.而KITTI数据集中不同序列的速度和工况差异很大,仅使用固定的距离和角度阈值很难精确地选择关键帧.试验结果如表1和表2所示,与K-LOAM相比,nk的精度和效率都显著降低,证实了本文基于特征变化筛选关键帧的方法的有效性和稳健性.值得注意的是,01序列的精度下降最为显著,因为它是在高速公路场景中录制的,最高速度为96 km/h.
CHENX, MILIOTOA, PALAZZOLOE,et al .SuMa:efficient LiDAR-based semantic SLAM[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Macau,China. IEEE,2019:4530-4537.
[2]
WANGH, WANGC, XIEL H .Intensity-SLAM:intensity assisted localization and mapping for large scale environment[J].IEEE Robotics and Automation Letters,2021,6(2):1715-1721.
[3]
ZHENGX, ZHUJ K .Traj-LO:in defense of LiDAR-only odometry using an effective continuous-time trajectory[J].IEEE Robotics and Automation Letters,2024,9(2):1961-1968.
[4]
BESLP J, MCKAYN D .A method for registration of 3-D shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2): 239-256.
[5]
VIZZOI, GUADAGNINOT, MERSCHB,et al .KISS-ICP:in defense of point-to-point ICP-simple,accurate,and robust registration if done the right way[J]. IEEE Robotics and Automation Letters, 2023, 8(2) :1029-1036.
[6]
CHENK, LOPEZB T, AGHA-MOHAMMADIA A,et al .Direct LiDAR odometry:fast localization with dense point clouds[J].IEEE Robotics and Automation Letters,2022,7(2):2000-2007.
[7]
DELLENBACHP, DESCHAUDJ E, JACQUETB,et al .CT-ICP:real-time elastic LiDAR odometry with loop closure[C]//2022 International Conference on Robotics and Automation (ICRA). Philadelphia,PA,USA. IEEE,2022:5580-5586.
[8]
XUW, CAIY X, HED J,et al .FAST-LIO2:fast direct LiDAR-inertial odometry[J]. IEEE Transactions on Robotics, 2022, 38(4): 2053-2073.
[9]
ZHANGJ, SINGHS .LOAM:lidar odometry and mapping in real-time[C]//Robotics:Science and Systems X. Robotics:Science and Systems Foundation, 2014, 2(9): 1-9.
[10]
CHENS B, MAH, JIANGC H,et al .NDT-LOAM:a real-time lidar odometry and mapping with weighted NDT and LFA[J].IEEE Sensors Journal,2022,22(4):3660-3671.
[11]
ALI W, LIUP L, YINGR D,et al .A feature based laser SLAM using rasterized images of 3D point cloud[J].IEEE Sensors Journal,2021,21(21):24422-24430.
[12]
ZHENGX, ZHUJ K .Efficient LiDAR odometry for autonomous driving[J].IEEE Robotics and Automation Letters,2021,6(4):8458-8465.
[13]
YEH Y, CHENY Y, LIUM .Tightly coupled 3D lidar inertial odometry and mapping[C]//2019 International Conference on Robotics and Automation (ICRA). Montreal,QC,Canada. IEEE,2019:3144-3150.
[14]
WANGH, WANGC, CHENC L,et al .F-LOAM:fast LiDAR odometry and mapping[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Prague,Czech Republic. IEEE,2021:4390-4396.
[15]
PANY, XIAOP C, HEY J,et al .MULLS:versatile LiDAR SLAM via multi-metric linear least square[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Xi’an,China. IEEE, 2021: 11633-11640.
[16]
SHANT X, ENGLOTB .LeGO-LOAM:lightweight and ground-optimized lidar odometry and mapping on variable terrain[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid, Spain. IEEE,2018:4758-4765.
[17]
SHANT X, ENGLOTB, MEYERSD,et al .LIO-SAM:tightly-coupled lidar inertial odometry via smoothing and mapping[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Las Vegas,NV,USA. IEEE,2020:5135-5142.
[18]
LIK L, LIM, HANEBECKU D .Towards high-performance solid-state-LiDAR-inertial odometry and mapping[J].IEEE Robotics and Automation Letters,2021,6(3):5167-5174.
[19]
SHENB K, XIEW M, PENGX D,et al .LIO-SAM++:a lidar-inertial semantic SLAM with association optimization and keyframe selection[J].Sensors,2024,24(23):7546.
[20]
ZUL N, WEIC R, SUNQ Q,et al .Adaptive keyframe selection strategy of visual SLAM in complex poses[J].IEEE Sensors Journal,2025,25(1):1756-1767.
[21]
LINY, DONGH Q, YEW T,et al .InfoLa-SLAM:efficient lidar-based lightweight simultaneous localization and mapping with information-based keyframe selection and landmarks assisted relocalization[J].Remote Sensing,2023,15(18):4627.
[22]
DUANY F, PENGJ, ZHANGY,et al .PFilter:building persistent maps through feature filtering for fast and accurate LiDAR-based SLAM[C]//2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Kyoto,Japan. IEEE, 2022: 11087-11093.
[23]
LIW, HUY, HANY H,et al .KFS-LIO:key-feature selection for lightweight lidar inertial odometry[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Xi’an, China. IEEE,2021:5042-5048.
[24]
CHANGD X, HUANGS J, ZHANGR B,et al .WiCRF2:multi-weighted LiDAR odometry and mapping with motion observability features[J].IEEE Sensors Journal,2023,23(17):20236-20246.
[25]
ZHOUZ B, YANGM, WANGC X,et al .ROI-cloud:a key region extraction method for LiDAR odometry and localization[C]//2020 IEEE International Conference on Robotics and Automation (ICRA). Paris,France. IEEE,2020:3312-3318.
[26]
KIMG, KIMA .Scan context:egocentric spatial descriptor for place recognition within 3D point cloud map[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid,Spain. IEEE, 2018: 4802-4809.
[27]
WANGY, SUNZ Z, XUC Z,et al .LiDAR iris for loop-closure detection[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Las Vegas,NV,USA. IEEE, 2020: 5769-5775.
[28]
CHENX, MILIOTOA, PALAZZOLOE,et al .SuMa++:efficient LiDAR-based semantic SLAM[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Macau,China. IEEE,2019:4530-4537.
[29]
MUR-ARTALR, MONTIELJ M M, TARDÓSJ D .ORB-SLAM:a versatile and accurate monocular SLAM system[J].IEEE Transactions on Robotics,2015,31(5):1147-1163.
[30]
ZHANGJ, KAESSM, SINGHS .On degeneracy of optimization-based state estimation problems[C]//2016 IEEE International Conference on Robotics and Automation (ICRA). Stockholm,Sweden. IEEE,2016:809-816.